Learning
Download as PPTX, PDF3 likes1,271 views
The document discusses different types of machine learning, including supervised learning where algorithms are trained using labeled examples, unsupervised learning which explores unlabeled data to find structures, semi-supervised learning which uses both labeled and unlabeled data, and reinforcement learning where an agent learns through trial and error interactions with an environment. It also covers topics such as natural language processing, ensemble learning techniques like boosting and bagging, and applications of machine learning like image recognition, medical diagnosis, and fraud detection. The document provides an overview of key concepts in machine learning including how learning systems work and the different steps involved in natural language processing.
Learning
- 1. Learning Amar Jukuntla Vignan’s Foundation For Science, Technology and Research (Deemed to be University)
- 2. Definition •Learning covers a broad range of processes •To gain • Knowledge • Or understand of • Or skill in • By study, instruction, or experience
- 3. Learning • Learning is essential for unknown environments, • i.e., when designer lacks omniscience • Learning is useful as a system construction method, • i.e., expose the agent to reality rather than trying to write it down • Learning modifies the agent's decision mechanisms to improve performance An agent is learning if it improves its performance on future tasks after making observations about the world
- 4. Why Learning? •Three main reasons •First, the designers cannot anticipate all possible situations that the agent might find itself in. •Second, the designers cannot anticipate all changes over time. •Third, sometimes human programmers have no idea how to program a solution themselves.
- 5. Forms of Learning • Any component of an agent can be improved by learning from data. The improvements, and the techniques used to make them, depend on four major factors: • Which component is to be improved • What prior knowledge the agent already has. • What representation is used for the data and the component. • What feedback is available to learn from.
- 6. Components to be learned • The components of these agents include: A direct mapping from conditions on the current state to actions. A means to infer relevant properties of the world from the percept sequence. Information about the way the world evolves and about the results of possible actions the agent can take. Utility information indicating the desirability of world states. Action-value information indicating the desirability of actions. Goals that describe classes of states whose achievement maximizes the agent’s utility.
- 7. Representatio n and prior knowledge • We have seen several examples of representations for agent components: propositional and first-order logical sentences for the components in a logical agent;
- 8. Feedback to learn from • There are three types of feedback that determine the three main types of learning: • Supervised learning: correct answers for each example (or) the agent observes some example input–output pairs and learns a function that maps from input to output • Unsupervised learning: correct answers not given (or) the agent learns patterns in the input even though no explicit feedback is supplied. Example: Clustering. • Reinforcement learning: occasional positive and/or negative rewards (or) the agent learns from a series of reinforcements—rewards or punishments.
- 9. Example Performance Element Component Representation Feedback Alpha-Beta Pruning Eval. Funtion Weighted Linear Function Win/Loss Logical Agent Transition Model Successor State- axioms Outcome Utility-Based Agent Transition Model Dynamic Bayes Network Outcome Simple Reflex Agent Percept-action Neural Network Correction action
- 11. Summary of Learning • Any situation in which both the inputs and outputs of a component can be perceived is called supervised learning. • In learning the condition-action component, the agent receives some evaluation of its action but is not told the correct action. This is called reinforcement learning. • Learning when there is no hint at all about the correct outputs is called unsupervised learning.
- 12. Inductive Learning This involves the process of learning by example -- where a system tries to induce a general rule from a set of observed instances.
- 13. Continue… • This involves classification -- assigning, to a particular input, the name of a class to which it belongs. Classification is important to many problem solving tasks. • A learning system has to be capable of evolving its own class descriptions: • Initial class definitions may not be adequate. • The world may not be well understood or rapidly changing. • The task of constructing class definitions is called induction or concept learning
- 14. Continue… • Simplest form: learn a function from examples f is the target function An example is a pair (x, f(x)) • Problem: find a hypothesis h such that h ≈ f given a training set of examples • This is a highly simplified model of real learning: • Ignores prior knowledge • Assumes a deterministic, observable environment • Assumes examples are given • Assume that the agent wants to learn m f (why?)
- 15. Continue… • Construct/adjust h to agree with f on training set • (h is consistent if it agrees with f on all examples) • E.g., curve fitting: The simplest hypothesis consistent with the data is called Ockham’s razor
- 16. Learning Decision Trees Decision tree induction is one of the simplest and yet most successful forms of machine learning.
- 17. Continue… • We first describe the representation— the hypothesis space—and then show how to learn a good hypothesis.
- 18. Representation • A Decision Tree takes as input an object given by a set of properties, output a Boolean value (yes/no decision). • Each internal node in the tree corresponds to test of one of the properties. Branches are labelled with the possible values of the test. • Aim: Learn goal concept (goal predicate) from examples • Learning element: Algorithm that builds up the decision tree. • Performance element: decision procedure given by the tree
- 20. Continue… • A Boolean decision tree is logically equivalent to the assertion that the goal attribute is true, if and only if the input attributes satisfy one of the paths leading to a leaf with value true. Writing this out in propositional logic, we have Goal ⇔ (Path1 ∨ Path2 ∨ . . . .) • where each Path is a conjunction of attribute-value tests required to follow that path. Thus, the whole expression is equivalent to disjunctive normal form which means that any function in propositional logic can be expressed as a decision tree. Path = (Patrons =Full ∧ WaitEstimate =0–10)
- 21. Example • Problem to wait for a table at a restaurant. A decision tree decides whether to wait or not in a given situation. • Attributes: • Alternate: alternative restaurant nearby • Bar: bar area to wait • Fri/Sat: true on Fridays and Saturdays • Hungry: whether we are hungry • Patrons: how many people in restaurant (none, some, or full) • price: price range (£ , £ £ , £ £ £ )
- 22. Continue… • raining: raining outside • reservation: whether we made a reservation • type: kind of restaurant (French, Italian, Thai, or Burger) • WaitEstimate: estimated wait (<10, 10-30,30-60,>60)
- 27. How to pick nodes? • For a training set containing p positive examples and n negative examples, we have: H 𝒑 𝒑+𝒏 , 𝒏 𝒑+𝒏 = − 𝒑 𝒑+𝒏 𝐥𝐨𝐠 𝟐 𝒑 𝒑+𝒏 − 𝒏 𝒑+𝒏 𝐥𝐨𝐠 𝟐 𝒏 𝒑+𝒏 • A chosen attribute A, with K distinct values, divides the training set E into subsets E1, … , EK. • The Expected Entropy (EH) remaining after trying attribute A (with branches i=1,2,…,K) is EH(A)= 𝒊=𝟏 𝒌 𝒑 𝒊+𝒏 𝒊 𝒑+𝒏 𝑯 𝒑 𝒑+𝒏 , 𝒏 𝒑+𝒏
- 28. Continue… • Information gain (I) or reduction in entropy for this attribute is: 𝐼 𝐴 =H 𝒑 𝒑+𝒏 , 𝒏 𝒑+𝒏 -EH(A) • Example; • I(Patrons)=H 𝟔 𝟏𝟐 , 𝟔 𝟏𝟐 - 2 12 H 𝟎 𝟐 , 𝟐 𝟐 + 4 12 H 𝟒 𝟒 , 𝟎 𝟒 + 6 12 H 𝟐 𝟔 , 𝟒 𝟔 = 𝟎. 𝟓𝟒𝟏𝒃𝒊𝒕𝒔
- 29. How to select next node?? • Given Patrons as root node, the next attribute chosen is Hungry?, with IG(Hungry?) = I(1/3, 2/3) – ( 2/3*1 + 1/3*0) = 0.252
- 30. Final decision tree induced by 12- example training set
- 31. Continue… •Decision Tree Pruning •Cross Validation •Training Sets •Test Cases •Validation Set
- 33. Continue… •Ensemble learning is a machine learning paradigm where multiple learners are trained to solve the same problem. In contrast to ordinary machine learning approaches which try to learn one hypothesis from training data, ensemble methods try to construct a set of hypotheses and combine them to use.
- 34. Continue… • Ensemble learning helps improve machine learning results by combining several models. • This approach allows the production of better predictive performance compared to a single model. • Ensemble methods are meta-algorithms that combine several machine learning techniques into one predictive model in order to decrease variance(bagging), bias (boosting), or improve predictions (stacking).
- 36. Boosting • Boosting refers to a family of algorithms that are able to convert weak learners to strong learners. • The main principle of boosting is to fit a sequence of weak learners− models that are only slightly better than random guessing, such as small decision trees− to weighted versions of the data. • More weight is given to examples that were misclassified by earlier rounds. • The predictions are then combined through a weighted majority vote (classification) or a weighted sum (regression) to produce the final prediction.
- 37. Continue… • The principal difference between boosting and the committee methods, such as bagging, is that base learners are trained in sequence on a weighted version of the data. • The algorithm below describes the most widely used form of boosting algorithm called AdaBoost, which stands for adaptive boosting.
- 42. Continue… • Natural Language Processing (NLP) refers to AI method of communicating with an intelligent systems using a natural language such as English. • Processing of Natural Language is required when you want an intelligent system like robot to perform as per your instructions, when you want to hear decision from a dialogue based clinical expert system, etc. • The field of NLP involves making computers to perform useful tasks with the natural languages humans use. The input and output of an NLP system can be − • Speech • Written Text
- 43. Continue… • To process written text, we need: • lexical, syntactic, semantic knowledge about the language • discourse information, real world knowledge • To process spoken language, we need everything required to process written text, plus the challenges of speech recognition and speech synthesis.
- 44. Components of NLP •Natural Language Understanding (NLU) •Understanding involves the following tasks − • Mapping the given input in natural language into useful representations. • Analyzing different aspects of the language.
- 45. Continue... •Natural Language Generation (NLG) • It is the process of producing meaningful phrases and sentences in the form of natural language from some internal representation. • It involves − • Text planning − It includes retrieving the relevant content from knowledge base. • Sentence planning − It includes choosing required words, forming meaningful phrases, setting tone of the sentence. • Text Realization − It is mapping sentence plan into sentence structure. The NLU is harder than NLG.
- 46. Difficulties in NLU • NL has an extremely rich form and structure. • It is very ambiguous. There can be different levels of ambiguity − • Lexical ambiguity − It is at very primitive level such as word-level. • For example, treating the word “board” as noun or verb? • Syntax Level ambiguity − A sentence can be parsed in different ways.
- 47. Continue… • For example, “He lifted the beetle with red cap.” − Did he use cap to lift the beetle or he lifted a beetle that had red cap? • Referential ambiguity − Referring to something using pronouns. For example, Rima went to Gauri. She said, “I am tired.” − Exactly who is tired? • One input can mean different meanings. Many inputs can mean the same thing.
- 48. NLP Terminology • Phonology − It is study of organizing sound systematically. • Morphology − It is a study of construction of words from primitive meaningful units. • Morpheme − It is primitive unit of meaning in a language. • Syntax − It refers to arranging words to make a sentence. It also involves determining the structural role of words in the sentence and in phrases.
- 49. Continue… • Semantics − It is concerned with the meaning of words and how to combine words into meaningful phrases and sentences. • Pragmatics − It deals with using and understanding sentences in different situations and how the interpretation of the sentence is affected. • Discourse − It deals with how the immediately preceding sentence can affect the interpretation of the next sentence. • World Knowledge − It includes the general knowledge about the world.
- 50. Steps in NLP •There are general five steps − •Lexical Analysis •Syntactic Analysis (Parsing) •Semantic Analysis •Discourse Integration •Pragmatic Analysis
- 51. Continue… • Lexical Analysis − It involves identifying and analyzing the structure of words. Lexicon of a language means the collection of words and phrases in a language. Lexical analysis is dividing the whole chunk of txt into paragraphs, sentences, and words. • Syntactic Analysis (Parsing) − It involves analysis of words in the sentence for grammar and arranging words in a manner that shows the relationship among the words. The sentence such as “The school goes to boy” is rejected by English syntactic analyzer.
- 52. Continue… • Semantic Analysis − It draws the exact meaning or the dictionary meaning from the text. The text is checked for meaningfulness. It is done by mapping syntactic structures and objects in the task domain. The semantic analyzer disregards sentence such as “hot ice-cream”. • Discourse Integration − The meaning of any sentence depends upon the meaning of the sentence just before it. In addition, it also brings about the meaning of immediately succeeding sentence. • Pragmatic Analysis − During this, what was said is re-interpreted on what it actually meant. It involves deriving those aspects of language which require real world knowledge.
- 53. Lexical Analysis1 Syntactic Analysis2 Semantic Analysis3 Discourse Integration4 Pragmatic Analysis5
- 54. Machine Learning
- 55. Introduction •A computer program is said to learn from a experience E with respect to the some class of tasks T and performance measure P, if its performance on tasks in T, on tasks in T as measured by P improves with experience E. DataPrediction Classification acting
- 56. Feed the Experience or Data Problem or Task Background Knowledge (Which will help the system) Solution and its corresponding performance measure Learner Reasoner Models
- 57. Applications Image Recognition Speech Recognition Medical Diagnosis Classification Prediction Regression Extraction Fraud Detection
- 58. Creating a Learner Choose Training Experience • Training Data Choose Target Function • How to represent a model (That is to be learned) Choose how to represent a target function Choose a learning Algorithm
- 59. Different Types of Learning Supervised Learning1 Unsupervised Learning2 Semi Supervised Learning3 Reinforcement Learning4
- 60. Supervised Learning • This kind of learning is possible when inputs and the outputs are clearly identified, and algorithms are trained using labeled examples.
- 61. Unsupervised Learning • Unlike supervised learning, unsupervised learning is used with data sets without historical data. An unsupervised learning algorithm explores surpassed data to find the structure. This kind of learning works best for transactional data; for instance, it helps in identifying customer segments and clusters with certain attributes
- 62. Semi-Supervised Learning • As the name suggests, semi-supervised learning is a bit of both supervised and unsupervised learning and uses both labeled and unlabeled data for training. In a typical scenario, the algorithm would use a small amount of labeled data with a large amount of unlabeled data.
- 63. Reinforcement Learning • This is a bit similar to the traditional type of data analysis; the algorithm discovers through trial and error and decides which action results in greater rewards. Three major components can be identified in reinforcement learning functionality: the agent, the environment, and the actions. The agent is the learner or decision-maker, the environment includes everything that the agent interacts with, and the actions are what the agent can do.
- 64. Reinforcement Learning • Reinforcement learning occurs when the agent chooses actions that maximize the expected reward over a given time. This is best achieved when the agent has a good policy to follow.
- 65. Perception
- 66. Perception •Perception appears to be an effortless activity for humans, it requires a significant amount of sophisticated computation. •The goal of vision is to extract information needed for tasks such as manipulation, navigation, and object recognition.
- 67. Why image processing??? •It is motivated by two major applications •Improvement of pictorial information for human perception. •Image processing for autonomous machine applications. •Efficient storage and transmission.
- 68. Basic Steps of Image Processing • Image Acquisition: An imaging sensor and the capability to digitalize the signal produced by the sensor. • Preprocessing: Enhance the image quality, filtering, contrast enhancement etc. • Segmentation: Partitions an image into constituent parts of objects. • Description/ Feature selection: Extracts description of image objects suitable for further computer processing.
- 69. Continue… •Recognition & interpretation: Assigning a label to the object based on the information provided by its descriptor. Interpretation assigns meaning to a set of labeled objects. •Knowledge Base: KB helps for efficient processing as well as inter module cooperation.
- 71. References • Artificial Intelligence Natural Language Processing - TutorialsPoint • http://web.cs.hacettepe.edu.tr/~ilyas/Courses/BIL711/lec01- overview.PPT • https://www.upwork.com/hiring/for-clients/artificial-intelligence-and- natural-language-processing-in-big-data/ • https://www.youtube.com/watch?v=T3PsRW6wZSY&list=PLlGkyYYWOSOs GU-XARWdIFsRAJQkyBrVj • https://www.simplilearn.com/what-is-machine-learning-and-why-it- matters-article • https://www.youtube.com/watch?v=CVV0TvNK6pk
- 72. References • http://users.cs.cf.ac.uk/Dave.Marshall/AI2/node144.html. • https://nptel.ac.in/courses/106106126/ • http://www2.hawaii.edu/~nreed/ics461/lectures/18learning.p df • http://www.cs.bham.ac.uk/~mmk/Teaching/AI/l3.html • https://cs.nju.edu.cn/zhouzh/zhouzh.files/publication/springer EBR09.pdf • https://blog.statsbot.co/ensemble-learning-d1dcd548e936 • https://www.scm.tees.ac.uk/isg/aia/nlp/NLP-overview.pdf